parse_screen

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses behavior: it returns a detailed JSON structure, saves a Set-of-Mark image, explains backend options, element cap of 300 with truncation flag, and id validity scope. This is comprehensive for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long but well-structured with bullet-like formatting and clear sections. Each part adds value, though it could be slightly more concise by removing redundant phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (multiple backends, return format, image saving, truncation, id validity), the description is quite complete. However, it lacks explanation of the parameters, which reduces completeness for a tool with two undocumented parameters. The output schema exists to document return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning the schema itself provides no parameter descriptions. The tool description does not explain the two parameters (instance, box_threshold) at all, leaving the agent without guidance on what they control. This is a significant gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it detects on-screen elements and returns them with ids and pixel centers. It uses a specific verb 'detect' and resource 'on-screen elements', and distinguishes from sibling tools like click_element (which uses the ids) and screenshot (which is a raw image).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool (to detect elements for clicking) and explains backends (local, basic, none) with their trade-offs. It also notes that ids are only valid until screen changes, implying re-parse after navigation, but does not explicitly state when not to use it versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.